Über diesen Podcast

Audio narrations of LessWrong posts.

250 Folgen · technology

LessWrong (30+ Karma)

Von LessWrong

5 weitere Apps

Neueste Folge“Current alignment training might be ineffective (and actively bad) in the age of RL” by Daniel Tanvor 4 Tagen13 Min.

Audio narrations of LessWrong posts.

“There is a channel to 900M weekly users. What goes in it?” by Charbel-Raphaëlvor 4 Tagen · 6 Min.
“I am refusing to work on Cloud TPUs” by Yair Halberstadtvor 4 Tagen · 4 Min.
“Deployment” by Nina Panicksseryvor 4 Tagen · 5 Min.
“Yet another concerning result on Astra’s no-CoT capabilities” by Christine Corryvor 4 Tagen · 14 Min.
“Alignment & Succession: The Two Bars of Alignment” by L Rudolf Lvor 4 Tagen · 26 Min.
“Anthropic and OpenAI haven’t published a plan for aligning superintelligence” by Zephaniah Roevor 4 Tagen · 3 Min.
“Consider how your global governance proposal is different from the EU Code of Practice” by David Matolcsivor 4 Tagen · 7 Min.
“Brand New AI Solves a Millennium Prize” by Zvivor 4 Tagen · 33 Min.
“Teleoperated Humans” by jefftkvor 4 Tagen · 11 Min.
“Mitigating Reward Hacking as Institutional Design” by berenvor 5 Tagen · 57 Min.